What can NVIDIA GeForce RTX 3080 16GB (Mobile) run locally?

69 models fit comfortably on NVIDIA GeForce RTX 3080 16GB (Mobile) with 32 GB system RAM. 62 more run with tradeoffs. Top pick: CodeGemma 7B.

What's the recommended runner for this hardware?

llama.cpp / Ollama (CUDA). This is the runner that gives best tokens-per-second on NVIDIA GeForce RTX 3080 16GB (Mobile) based on windows support and the GPU backend.

What can NVIDIA GeForce RTX 3080 16GB (Mobile) run for coding?

Build: NVIDIA GeForce RTX 3080 16GB (Mobile) + — + 32 GB RAM (windows)

Memory: 16 GB VRAM + 32 GB system RAM

Runner: llama.cpp / Ollama (CUDA)

Any Chat Coding Agents Reasoning Vision Long context Creative

Runs comfortably
69 models

Ranked by fit for coding use case + predicted speed. Click a row for VRAM breakdown.

#1CodeGemma 7B

gemma

Commercial OK

Quant: Q4_K_MContext: 8,192VRAM: 9.7 GBHeadroom: 6.3 GBTTFT: noticeable

ollama run codegemma:7b

tok/s

Estimated

Weights

4.20 GB

KV cache

3.50 GB

Activations

0.22 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~717 ms (noticeable)

Model details →

#2Qwen 3 8B

qwen

Commercial OK

Quant: Q4_K_MContext: 8,192VRAM: 10.8 GBHeadroom: 5.2 GBTTFT: noticeable

ollama run qwen3:8b

tok/s

Estimated

Weights

4.80 GB

KV cache

4.00 GB

Activations

0.25 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~819 ms (noticeable)

Model details →

#3Qwen 2.5 7B Instruct

qwen

Commercial OK

Quant: Q8_0Context: 8,192VRAM: 10.8 GBHeadroom: 5.2 GBTTFT: noticeable

ollama run qwen2.5:7b

tok/s

Estimated

Weights

8.10 GB

KV cache

0.47 GB

Activations

0.41 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~717 ms (noticeable)

Model details →

#4Llama 3.1 8B Instruct

llama

Commercial OK

Quant: Q8_0Context: 8,192VRAM: 11.8 GBHeadroom: 4.2 GBTTFT: noticeable

ollama run llama3.1:8b

tok/s

Estimated

Weights

8.50 GB

KV cache

1.07 GB

Activations

0.43 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~819 ms (noticeable)

Model details →

#5Qwen 2.5 Coder 3B

qwen

Commercial OK

Quant: Q4_K_MContext: 8,192VRAM: 5.3 GBHeadroom: 10.7 GBTTFT: fast

184

tok/s

Estimated

Weights

1.90 GB

KV cache

1.50 GB

Activations

0.10 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~307 ms (fast)

Model details →

#6StarCoder 2 3B

other

Commercial OK

Quant: Q4_K_MContext: 8,192VRAM: 5.4 GBHeadroom: 10.6 GBTTFT: fast

184

tok/s

Estimated

Weights

2.00 GB

KV cache

1.50 GB

Activations

0.11 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~307 ms (fast)

Model details →

#7Codestral Mamba 7B

mistral

Commercial OK

Quant: Q4_K_MContext: 8,192VRAM: 9.7 GBHeadroom: 6.3 GBTTFT: noticeable

tok/s

Estimated

Weights

4.20 GB

KV cache

3.50 GB

Activations

0.22 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~717 ms (noticeable)

Model details →

#8StarCoder 2 7B

other

Commercial OK

Quant: Q4_K_MContext: 8,192VRAM: 9.9 GBHeadroom: 6.1 GBTTFT: noticeable

tok/s

Estimated

Weights

4.40 GB

KV cache

3.50 GB

Activations

0.23 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~717 ms (noticeable)

Model details →

#9OpenCoder 8B

opencoder

Commercial OK

Quant: Q4_K_MContext: 8,192VRAM: 10.7 GBHeadroom: 5.3 GBTTFT: noticeable

tok/s

Estimated

Weights

4.70 GB

KV cache

4.00 GB

Activations

0.24 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~819 ms (noticeable)

Model details →

#10Yi Coder 9B

Commercial OK

Quant: Q4_K_MContext: 8,192VRAM: 12.0 GBHeadroom: 4.0 GBTTFT: noticeable

tok/s

Estimated

Weights

5.40 GB

KV cache

4.50 GB

Activations

0.28 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~922 ms (noticeable)

Model details →

#11Phi-3.5 Vision

4.2B

phi

Commercial OK

Quant: Q4_K_MContext: 8,192VRAM: 6.5 GBHeadroom: 9.5 GBTTFT: fast

131

tok/s

Estimated

Weights

2.50 GB

KV cache

2.10 GB

Activations

0.13 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~430 ms (fast)

Model details →

#12Falcon 3 3B Instruct

falcon

Commercial OK

Quant: Q4_K_MContext: 8,192VRAM: 5.1 GBHeadroom: 10.9 GBTTFT: fast

184

tok/s

Estimated

Weights

1.70 GB

KV cache

1.50 GB

Activations

0.09 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~307 ms (fast)

Model details →

Runs with tradeoffs
62 models

Tight VRAM, partial CPU offload, or context-limited.

DeepSeek Coder V2 Lite (16B)

16B

deepseek

Commercial OK

Quant: Q4_K_MContext: 2,048VRAM: 13.8 GBHeadroom: 2.2 GBTTFT: noticeable

• Tight VRAM fit — only 2.2 GB headroom left for context growth

ollama run deepseek-coder-v2:16b

tok/s

Estimated

Weights

9.50 GB

KV cache

2.00 GB

Activations

0.48 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~1638 ms (noticeable)

Model details →

Codestral 22B

22B

mistral

Quant: Q4_K_MContext: 8,192VRAM: 26.5 GBHeadroom: 8.7 GBTTFT: slow

• Partial CPU offload: ~40% of layers run on CPU

ollama run codestral:22b

tok/s

Estimated

Weights

13.00 GB

KV cache

11.00 GB

Activations

0.66 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~2253 ms (slow)

Model details →

Qwen 3 14B

14B

qwen

Commercial OK

Quant: Q4_K_MContext: 2,048VRAM: 12.4 GBHeadroom: 3.6 GBTTFT: noticeable

• Tight VRAM fit — only 3.6 GB headroom left for context growth

ollama run qwen3:14b

tok/s

Estimated

Weights

8.40 GB

KV cache

1.75 GB

Activations

0.42 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~1434 ms (noticeable)

Model details →

Qwen 2.5 14B Instruct

14B

qwen

Commercial OK

Quant: Q4_K_MContext: 2,048VRAM: 12.9 GBHeadroom: 3.1 GBTTFT: noticeable

• Tight VRAM fit — only 3.1 GB headroom left for context growth

ollama run qwen2.5:14b

tok/s

Estimated

Weights

8.90 GB

KV cache

1.75 GB

Activations

0.45 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~1434 ms (noticeable)

Model details →

Qwen 2.5 Coder 32B Instruct

32B

qwen

Commercial OK

Quant: Q4_K_MContext: 8,192VRAM: 23.9 GBHeadroom: 11.3 GBTTFT: slow

• Partial CPU offload: ~33% of layers run on CPU

ollama run qwen2.5-coder:32b

tok/s

Estimated

Weights

19.00 GB

KV cache

2.15 GB

Activations

0.96 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~3277 ms (slow)

Model details →

Qwen 3 30B-A3B

30B

qwen

Commercial OK

Quant: Q4_K_MContext: 2,048VRAM: 24.5 GBHeadroom: 10.7 GBTTFT: slow

• Partial CPU offload: ~35% of layers run on CPU

ollama run qwen3:30b

tok/s

Estimated

Weights

18.00 GB

KV cache

3.75 GB

Activations

0.90 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~3072 ms (slow)

Model details →

Gemma 4 31B Dense

31B

gemma

Commercial OK

Quant: Q4_K_MContext: 2,048VRAM: 24.6 GBHeadroom: 10.6 GBTTFT: slow

• Partial CPU offload: ~35% of layers run on CPU

ollama run gemma4:31b

tok/s

Estimated

Weights

18.00 GB

KV cache

3.88 GB

Activations

0.90 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~3174 ms (slow)

Model details →

Qwen 3 32B

32B

qwen

Commercial OK

Quant: Q4_K_MContext: 2,048VRAM: 25.8 GBHeadroom: 9.4 GBTTFT: slow

• Partial CPU offload: ~38% of layers run on CPU

ollama run qwen3:32b

tok/s

Estimated

Weights

19.00 GB

KV cache

4.00 GB

Activations

0.95 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~3277 ms (slow)

Model details →

What if you upgraded?

Hypothetical scenarios. We re-ran the compatibility engine for each.

+32 GB system RAM

Check the current price

Adds 32 GB to your CPU-offload working set. Helps when models don't quite fit in VRAM.

Unlocks: 28 new comfortable, 78 new tradeoff

• Qwen 3 0.6B
• Qwen 3 1.7B
• Gemma 3 270M
• SmolLM2 135M Instruct

Shop this upgrade↗

Upgrade to NVIDIA RTX 2080 Ti 22GB (China-mod)

Check the current price

22 GB VRAM (vs your 16 GB) plus a bandwidth jump from ~512 GB/s to ~616 GB/s.

Unlocks: 47 new comfortable

• Qwen 3 0.6B
• Qwen 3 1.7B
• Qwen 3 14B
• Gemma 3 270M

Add a second NVIDIA GeForce RTX 3080 16GB (Mobile)

Check the current price

Tensor parallelism splits the model across both cards, effectively doubling VRAM. Bandwidth doesn't double — runs ~1.5× the single-card speed in practice.

Unlocks: 78 new comfortable

• Qwen 3 0.6B
• Qwen 3 30B-A3B
• Qwen 2.5 Coder 32B Instruct
• Qwen 3 32B

Shop this upgrade↗

Some links above are affiliate links. We may earn a commission at no extra cost to you. How we make money.

Won't run
top 5 popular models

Need more memory than you have. Shown for orientation.

DeepSeek V4 Pro (1.6T MoE)

1600B

deepseek

Commercial OK